Pub Date : 2025-03-01DOI: 10.1016/j.sbi.2025.103022
Els Pardon , Alex Wohlkönig , Jan Steyaert
Nanobodies (Nbs), the variable domains of heavy-chain only antibodies that naturally occur in camelids, are exquisite molecular tools to stabilize dynamic proteins in unique functional conformations. Recent developments in Nb discovery allow to select allosteric Nbs that perturb the distribution of conformational ensembles of protein complexes that mediate signaling, leading to the allosteric modulation of the signals they transmit. Evidence is also accumulating that such conformational specific Nbs do not stabilize new conformational states but rather change the distribution of existing states to allosterically induce transitions, imprinted by the natural ligands of the system.
{"title":"Allosteric modulation of protein–protein interactions in signal transduction with Nanobodies","authors":"Els Pardon , Alex Wohlkönig , Jan Steyaert","doi":"10.1016/j.sbi.2025.103022","DOIUrl":"10.1016/j.sbi.2025.103022","url":null,"abstract":"<div><div>Nanobodies (Nbs), the variable domains of heavy-chain only antibodies that naturally occur in camelids, are exquisite molecular tools to stabilize dynamic proteins in unique functional conformations. Recent developments in Nb discovery allow to select allosteric Nbs that perturb the distribution of conformational ensembles of protein complexes that mediate signaling, leading to the allosteric modulation of the signals they transmit. Evidence is also accumulating that such conformational specific Nbs do not stabilize new conformational states but rather change the distribution of existing states to allosterically induce transitions, imprinted by the natural ligands of the system.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"92 ","pages":"Article 103022"},"PeriodicalIF":6.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.sbi.2025.103024
Bing-Rui Zhou, Benjamin Orris, Ruifang Guan, Tengfei Lian, Yawen Bai
Pioneer transcription factors possess the unique ability to bind to nucleosomal DNA and locally open closed chromatin, enabling the binding of additional chromatin-associated factors. These factors are pivotal in determining cell fate. Structural studies of pioneer transcription factors interacting with nucleosomes have predominantly relied on model systems incorporating canonical DNA motifs within synthetic, strongly positioned DNA. However, recent advances have revealed structures of several pioneer transcription factors bound to their native nucleosome targets at gene enhancers involved in cell reprogramming. These findings offer fresh insights into how pioneer transcription factors recognize and disrupt compact chromatin. In this review, we summarize these recent discoveries and explore their broader implications.
{"title":"Structural insights into the recognition of native nucleosomes by pioneer transcription factors","authors":"Bing-Rui Zhou, Benjamin Orris, Ruifang Guan, Tengfei Lian, Yawen Bai","doi":"10.1016/j.sbi.2025.103024","DOIUrl":"10.1016/j.sbi.2025.103024","url":null,"abstract":"<div><div>Pioneer transcription factors possess the unique ability to bind to nucleosomal DNA and locally open closed chromatin, enabling the binding of additional chromatin-associated factors. These factors are pivotal in determining cell fate. Structural studies of pioneer transcription factors interacting with nucleosomes have predominantly relied on model systems incorporating canonical DNA motifs within synthetic, strongly positioned DNA. However, recent advances have revealed structures of several pioneer transcription factors bound to their native nucleosome targets at gene enhancers involved in cell reprogramming. These findings offer fresh insights into how pioneer transcription factors recognize and disrupt compact chromatin. In this review, we summarize these recent discoveries and explore their broader implications.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"92 ","pages":"Article 103024"},"PeriodicalIF":6.1,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Missense variants can affect the severity of disease, choice of treatment, and treatment outcomes. While the number of known variants has been increasing at a rapid pace, available evidence of their clinical effect has been lagging behind, constituting a challenge for clinicians and researchers. Multiplexed assays of variant effects (MAVEs) are important to close the gap; nonetheless, computational predictions of pathogenicity are still often the only available data for scoring variants. Such methods are not designed to provide a mechanistic explanation for the effect of amino acid substitutions. To this purpose, we propose structure-based frameworks as ensemble methodologies, with each method tailored to predict a different aspect among those exerted by amino acid substitutions to link predicted pathogenicity to mechanistic indicators. We review available frameworks, as well as advancements in underlying structure-based methods that predict variant effects on several protein features, such as protein stability, biomolecular interactions, allostery, post-translational modifications, and more.
{"title":"Predicting the structure-altering mechanisms of disease variants","authors":"Matteo Arnaudi , Mattia Utichi , Matteo Tiberti , Elena Papaleo","doi":"10.1016/j.sbi.2025.102994","DOIUrl":"10.1016/j.sbi.2025.102994","url":null,"abstract":"<div><div>Missense variants can affect the severity of disease, choice of treatment, and treatment outcomes. While the number of known variants has been increasing at a rapid pace, available evidence of their clinical effect has been lagging behind, constituting a challenge for clinicians and researchers. Multiplexed assays of variant effects (MAVEs) are important to close the gap; nonetheless, computational predictions of pathogenicity are still often the only available data for scoring variants. Such methods are not designed to provide a mechanistic explanation for the effect of amino acid substitutions. To this purpose, we propose structure-based frameworks as ensemble methodologies, with each method tailored to predict a different aspect among those exerted by amino acid substitutions to link predicted pathogenicity to mechanistic indicators. We review available frameworks, as well as advancements in underlying structure-based methods that predict variant effects on several protein features, such as protein stability, biomolecular interactions, allostery, post-translational modifications, and more.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"91 ","pages":"Article 102994"},"PeriodicalIF":6.1,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-26DOI: 10.1016/j.sbi.2025.103007
Aidan C.A. Tomlinson , John E. Knox , Luc Brunsveld , Christian Ottmann , Jason K. Yano
Molecular glues are small molecules that nucleate novel or stabilize natural, protein–protein interactions resulting in a ternary complex. Their success in targeting difficult to drug proteins of interest has led to ever-increasing interest in their use as therapeutics and research tools. While molecular glues and their targets vary in structure, inspection of diverse ternary complexes reveals commonalities. Whether of high or low molecular weight, molecular glues are often rigid and form direct hydrophobic interactions with their target protein. There is growing evidence that these hotspots can accommodate multiple ternary complex binding modes and enable targeting of traditionally undruggable targets. Advances in screening from the molecular glue degrader literature and insights in structure-based drug design, especially from the non-degrading tri-complex work, are likely intersectional.
{"title":"The “three body solution”: Structural insights into molecular glues","authors":"Aidan C.A. Tomlinson , John E. Knox , Luc Brunsveld , Christian Ottmann , Jason K. Yano","doi":"10.1016/j.sbi.2025.103007","DOIUrl":"10.1016/j.sbi.2025.103007","url":null,"abstract":"<div><div>Molecular glues are small molecules that nucleate novel or stabilize natural, protein–protein interactions resulting in a ternary complex. Their success in targeting difficult to drug proteins of interest has led to ever-increasing interest in their use as therapeutics and research tools. While molecular glues and their targets vary in structure, inspection of diverse ternary complexes reveals commonalities. Whether of high or low molecular weight, molecular glues are often rigid and form direct hydrophobic interactions with their target protein. There is growing evidence that these hotspots can accommodate multiple ternary complex binding modes and enable targeting of traditionally undruggable targets. Advances in screening from the molecular glue degrader literature and insights in structure-based drug design, especially from the non-degrading tri-complex work, are likely intersectional.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"91 ","pages":"Article 103007"},"PeriodicalIF":6.1,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-24DOI: 10.1016/j.sbi.2025.103020
Jaemin Sim , Dongwoo Kim , Bomin Kim , Jieun Choi , Juyong Lee
Structure-based drug discovery is a fundamental approach in modern drug development, leveraging computational models to predict protein-ligand interactions. AI-driven methodologies are significantly improving key aspects of the field, including ligand binding site prediction, protein-ligand binding pose estimation, scoring function development, and virtual screening. In this review, we summarize the recent AI-driven advances in various protein-ligand interaction prediction tasks. Traditional docking methods based on empirical scoring functions often lack accuracy, whereas AI models, including graph neural networks, mixture density networks, transformers, and diffusion models, have enhanced predictive performance. Ligand binding site prediction has been refined using geometric deep learning and sequence-based embeddings, aiding in the identification of potential druggable target sites. Binding pose prediction has evolved with sampling-based and regression-based models, as well as protein-ligand co-generation frameworks. AI-powered scoring functions now integrate physical constraints and deep learning techniques to improve binding affinity estimation, leading to more robust virtual screening strategies. Despite these advances, generalization across diverse protein-ligand pairs remains a challenge. As AI technologies continue to evolve, they are expected to revolutionize molecular docking and affinity prediction, increasing both the accuracy and efficiency of structure-based drug discovery.
{"title":"Recent advances in AI-driven protein-ligand interaction predictions","authors":"Jaemin Sim , Dongwoo Kim , Bomin Kim , Jieun Choi , Juyong Lee","doi":"10.1016/j.sbi.2025.103020","DOIUrl":"10.1016/j.sbi.2025.103020","url":null,"abstract":"<div><div>Structure-based drug discovery is a fundamental approach in modern drug development, leveraging computational models to predict protein-ligand interactions. AI-driven methodologies are significantly improving key aspects of the field, including ligand binding site prediction, protein-ligand binding pose estimation, scoring function development, and virtual screening. In this review, we summarize the recent AI-driven advances in various protein-ligand interaction prediction tasks. Traditional docking methods based on empirical scoring functions often lack accuracy, whereas AI models, including graph neural networks, mixture density networks, transformers, and diffusion models, have enhanced predictive performance. Ligand binding site prediction has been refined using geometric deep learning and sequence-based embeddings, aiding in the identification of potential druggable target sites. Binding pose prediction has evolved with sampling-based and regression-based models, as well as protein-ligand co-generation frameworks. AI-powered scoring functions now integrate physical constraints and deep learning techniques to improve binding affinity estimation, leading to more robust virtual screening strategies. Despite these advances, generalization across diverse protein-ligand pairs remains a challenge. As AI technologies continue to evolve, they are expected to revolutionize molecular docking and affinity prediction, increasing both the accuracy and efficiency of structure-based drug discovery.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"92 ","pages":"Article 103020"},"PeriodicalIF":6.1,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.sbi.2025.103023
Lukas Gerasimavicius , Sarah A. Teichmann , Joseph A. Marsh
Despite massive sequencing efforts, understanding the difference between human pathogenic and benign variants remains a challenge. Computational variant effect predictors (VEPs) have emerged as essential tools for assessing the impact of genetic variants, although their performance varies. Initially, sequence-based methods dominated the field, but recent advances, particularly in protein structure prediction technologies like AlphaFold, have led to an increased utilization of structural information by VEPs aimed at scoring human missense variants. This review highlights the progress in integrating structural information into VEPs, showcasing novel models such as AlphaMissense, PrimateAI-3D, and CPT-1 that demonstrate improved variant evaluation. Structural data offers more interpretability, especially for non-loss-of-function variants, and provides insights into complex variant interactions in vivo. As the field advances, utilizing biomolecular complex structures will be pivotal for future VEP development, with recent breakthroughs in protein-ligand and protein-nucleic acid complex prediction offering new avenues.
{"title":"Leveraging protein structural information to improve variant effect prediction","authors":"Lukas Gerasimavicius , Sarah A. Teichmann , Joseph A. Marsh","doi":"10.1016/j.sbi.2025.103023","DOIUrl":"10.1016/j.sbi.2025.103023","url":null,"abstract":"<div><div>Despite massive sequencing efforts, understanding the difference between human pathogenic and benign variants remains a challenge. Computational variant effect predictors (VEPs) have emerged as essential tools for assessing the impact of genetic variants, although their performance varies. Initially, sequence-based methods dominated the field, but recent advances, particularly in protein structure prediction technologies like AlphaFold, have led to an increased utilization of structural information by VEPs aimed at scoring human missense variants. This review highlights the progress in integrating structural information into VEPs, showcasing novel models such as AlphaMissense, PrimateAI-3D, and CPT-1 that demonstrate improved variant evaluation. Structural data offers more interpretability, especially for non-loss-of-function variants, and provides insights into complex variant interactions <em>in vivo</em>. As the field advances, utilizing biomolecular complex structures will be pivotal for future VEP development, with recent breakthroughs in protein-ligand and protein-nucleic acid complex prediction offering new avenues.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"92 ","pages":"Article 103023"},"PeriodicalIF":6.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-21DOI: 10.1016/j.sbi.2025.103001
Youdong Mao
Rational structure-based drug design (SBDD) depends on high-resolution structural models of target macromolecules or their complexes. However, the lack of atomic-level functional molecular dynamics hinders the applications of SBDD and limits their effective translation into clinically successful therapeutics. Time-resolved cryo-electron microscopy (cryo-EM) has emerged as a powerful tool in structural biology, capable of capturing high-resolution snapshots of biomolecular machines in action. Unlike molecular dynamics (MD) simulations, time-resolved cryo-EM can visualize rare intermediate states across a broader range of timescales, providing invaluable insights into drug-binding kinetics, dynamic protein-ligand interactions, and allosteric regulation. Integration of time-resolved cryo-EM with machine learning (ML) and artificial intelligence (AI) expands SBDD into a dynamics-based approach, allowing for more accurate pharmacological modeling of challenging drug targets that are beyond the reach of MD simulations. Time-resolved cryo-EM can help researchers to identify novel druggable conformations, overcome drug resistance, and reduce the time and cost of clinical translations. Despite current challenges, the future development of time-resolved cryo-EM with AI and in situ imaging strategy, such as cryo-electron tomography, holds the potential to revolutionize drug discovery by revealing in vivo molecular dynamics of drug actions at an unprecedented spatiotemporal scale.
{"title":"Dynamics-based drug discovery by time-resolved cryo-EM","authors":"Youdong Mao","doi":"10.1016/j.sbi.2025.103001","DOIUrl":"10.1016/j.sbi.2025.103001","url":null,"abstract":"<div><div>Rational structure-based drug design (SBDD) depends on high-resolution structural models of target macromolecules or their complexes. However, the lack of atomic-level functional molecular dynamics hinders the applications of SBDD and limits their effective translation into clinically successful therapeutics. Time-resolved cryo-electron microscopy (cryo-EM) has emerged as a powerful tool in structural biology, capable of capturing high-resolution snapshots of biomolecular machines in action. Unlike molecular dynamics (MD) simulations, time-resolved cryo-EM can visualize rare intermediate states across a broader range of timescales, providing invaluable insights into drug-binding kinetics, dynamic protein-ligand interactions, and allosteric regulation. Integration of time-resolved cryo-EM with machine learning (ML) and artificial intelligence (AI) expands SBDD into a dynamics-based approach, allowing for more accurate pharmacological modeling of challenging drug targets that are beyond the reach of MD simulations. Time-resolved cryo-EM can help researchers to identify novel druggable conformations, overcome drug resistance, and reduce the time and cost of clinical translations. Despite current challenges, the future development of time-resolved cryo-EM with AI and <em>in situ</em> imaging strategy, such as cryo-electron tomography, holds the potential to revolutionize drug discovery by revealing <em>in vivo</em> molecular dynamics of drug actions at an unprecedented spatiotemporal scale.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"91 ","pages":"Article 103001"},"PeriodicalIF":6.1,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-21DOI: 10.1016/j.sbi.2025.103017
Atabey Ünlü , Erva Ulusoy , Melih Gökay Yiğit , Melih Darcan , Tunca Doğan
Identifying new drug candidates remains a critical and complex challenge in drug development. Recent advances in deep learning have demonstrated significant potential to accelerate this process, particularly through the use of protein language models (pLMs). These models aim to effectively capture the structural and functional properties of proteins by embedding them in high-dimensional spaces, thereby providing powerful tools for predictive tasks. This review examines the application of pLMs in drug-target interaction (DTI) prediction, addressing both small-molecule and protein-based therapeutics. We explore diverse methodologies, including end-to-end learning models and those that leverage pre-trained foundational pLMs. Furthermore, we highlight the role of heterogeneous data integration—ranging from protein structures to knowledge graphs—to improve the accuracy of DTI predictions. Despite notable progress, challenges persist in accurately identifying DTIs, mainly due to data-related limitations and algorithmic constraints. Future research directions include utilising multimodal learning approaches, incorporating temporal/dynamic interaction data into training, and employing novel deep learning architectures to refine protein representations, gain a deeper understanding of biological context regarding molecular interactions, and, thus, advance the DTI prediction field.
{"title":"Protein language models for predicting drug–target interactions: Novel approaches, emerging methods, and future directions","authors":"Atabey Ünlü , Erva Ulusoy , Melih Gökay Yiğit , Melih Darcan , Tunca Doğan","doi":"10.1016/j.sbi.2025.103017","DOIUrl":"10.1016/j.sbi.2025.103017","url":null,"abstract":"<div><div>Identifying new drug candidates remains a critical and complex challenge in drug development. Recent advances in deep learning have demonstrated significant potential to accelerate this process, particularly through the use of protein language models (pLMs). These models aim to effectively capture the structural and functional properties of proteins by embedding them in high-dimensional spaces, thereby providing powerful tools for predictive tasks. This review examines the application of pLMs in drug-target interaction (DTI) prediction, addressing both small-molecule and protein-based therapeutics. We explore diverse methodologies, including end-to-end learning models and those that leverage pre-trained foundational pLMs. Furthermore, we highlight the role of heterogeneous data integration—ranging from protein structures to knowledge graphs—to improve the accuracy of DTI predictions. Despite notable progress, challenges persist in accurately identifying DTIs, mainly due to data-related limitations and algorithmic constraints. Future research directions include utilising multimodal learning approaches, incorporating temporal/dynamic interaction data into training, and employing novel deep learning architectures to refine protein representations, gain a deeper understanding of biological context regarding molecular interactions, and, thus, advance the DTI prediction field.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"91 ","pages":"Article 103017"},"PeriodicalIF":6.1,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-21DOI: 10.1016/j.sbi.2025.102986
Michael Heinzinger , Burkhard Rost
Large Language Models for proteins, namely protein Language Models (pLMs), have begun to provide an important alternative to capturing the information encoded in a protein sequence in computers. Arguably, pLMs have advanced importantly to understanding aspects of the language of life as written in proteins, and through this understanding, they are becoming an increasingly powerful means of advancing protein prediction, e.g., in the prediction of molecular function as expressed by identifying binding residues or variant effects. While benefitting from the same technology, protein structure prediction remains one of the few applications for which only using pLM embeddings from single sequences appears not to improve over or match the state-of-the-art. Fine-tuning foundation pLMs enhances efficiency and accuracy of solutions, in particular in cases with few experimental annotations. pLMs facilitate the integration of computational and experimental biology, of AI and wet-lab, in particular toward a new era of protein design.
{"title":"Teaching AI to speak protein","authors":"Michael Heinzinger , Burkhard Rost","doi":"10.1016/j.sbi.2025.102986","DOIUrl":"10.1016/j.sbi.2025.102986","url":null,"abstract":"<div><div>Large Language Models for proteins, namely protein Language Models (<u>pLMs</u>), have begun to provide an important alternative to capturing the information encoded in a protein sequence in computers. Arguably, pLMs have advanced importantly to understanding aspects of the <em>language of life</em> as written in proteins, and through this understanding, they are becoming an increasingly powerful means of advancing protein prediction, e.g., in the prediction of molecular function as expressed by identifying binding residues or variant effects. While benefitting from the same technology, protein structure prediction remains one of the few applications for which only using pLM embeddings from single sequences appears not to improve over or match the state-of-the-art. Fine-tuning foundation pLMs enhances efficiency and accuracy of solutions, in particular in cases with few experimental annotations. pLMs facilitate the integration of computational and experimental biology, of AI and wet-lab, in particular toward a new era of protein design.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"91 ","pages":"Article 102986"},"PeriodicalIF":6.1,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-20DOI: 10.1016/j.sbi.2025.103003
Yogesh Kalakoti, Airy Sanjeev, Björn Wallner
Proteins are dynamic molecules that transition between conformational states to perform their functions, and characterizing the protein ensemble is important for understanding biology and therapeutic applications. While recent breakthroughs in machine learning have enabled the prediction of high-quality static models of individual proteins, generating reliable estimates of their conformational ensembles remains a challenge. Several recent methods have tried to utilize the evolutionary and structural features captured by effective sequence-to-structure models to enhance conformational diversity in generated models. Most of these approaches involve adapting existing inference pipelines, such as AlphaFold 2, combined with sampling techniques to induce the generation of diverse conformational states. Here, we describe the general problem of predicting structural variations in protein systems, explain the methods designed to address this challenge, explore why they are effective, discuss their limitations, and suggest potential future directions.
{"title":"Prediction of structural variation","authors":"Yogesh Kalakoti, Airy Sanjeev, Björn Wallner","doi":"10.1016/j.sbi.2025.103003","DOIUrl":"10.1016/j.sbi.2025.103003","url":null,"abstract":"<div><div>Proteins are dynamic molecules that transition between conformational states to perform their functions, and characterizing the protein ensemble is important for understanding biology and therapeutic applications. While recent breakthroughs in machine learning have enabled the prediction of high-quality static models of individual proteins, generating reliable estimates of their conformational ensembles remains a challenge. Several recent methods have tried to utilize the evolutionary and structural features captured by effective sequence-to-structure models to enhance conformational diversity in generated models. Most of these approaches involve adapting existing inference pipelines, such as AlphaFold 2, combined with sampling techniques to induce the generation of diverse conformational states. Here, we describe the general problem of predicting structural variations in protein systems, explain the methods designed to address this challenge, explore why they are effective, discuss their limitations, and suggest potential future directions.</div></div>","PeriodicalId":10887,"journal":{"name":"Current opinion in structural biology","volume":"91 ","pages":"Article 103003"},"PeriodicalIF":6.1,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号